Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    programming keywords and function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.57
    }$,
    0.56
     在
    0.55
     는
    0.54
     bridle
    0.52
     सिलसिला
    0.52
     reinvigor
    0.52
    야
    0.51
     は
    0.51
     captivated
    0.50
    POSITIVE LOGITS
    in
    1.00
    ik
    0.88
    т
    0.87
    ة
    0.86
    to
    0.83
    í
    0.82
    ت
    0.81
    ing
    0.75
    and
    0.74
    á
    0.74
    Act Density 0.039%

    No Known Activations